Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multis
    -0.07
    όγ
    -0.07
     defin
    -0.07
     concentrating
    -0.06
     posters
    -0.06
    kin
    -0.06
     boundary
    -0.06
    -series
    -0.06
     walkers
    -0.06
     quienes
    -0.06
    POSITIVE LOGITS
    .registration
    0.07
    ’ya
    0.07
    jury
    0.07
     ит
    0.07
    _RETURNTRANSFER
    0.07
    .radio
    0.07
    ап
    0.06
     smugg
    0.06
     pursue
    0.06
    .setError
    0.06
    Act Density 0.000%

    No Known Activations